2015/05/26 by César F. Caiafa, Franco Pestilli, Caiafa, Cesar F. +1
Mathematics · Medicine · #Advanced MRI Techniques and Applications #Advanced Neuroimaging Techniques and Applications #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Mathematics #Methodology (stat.ME) #Numerical Analysis (math.NA) #Quantitative Methods (q-bio.QM) #Tensor decomposition and applications
paper · pdf · doi:10.48550/arxiv.1505.07170
openalex publication_date 2015/05/26 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28
The number of neuroimaging data sets publicly available is growing at fast\nrate. The increase in availability and resolution of neuroimaging data requires\nmodern approaches to signal processing for data analysis and results\nvalidation. We introduce the application of sparse multiway decomposition\nmethods (Caiafa and Cichocki, 2012) to linearized neuroimaging models. We show\nthat decomposed models are more compact but as accurate as full models and can\nbe successfully used for fast data analysis. We focus as example on a recent\nmodel for the evaluation of white matter connectomes (Pestilli et al, 2014). We\nshow that the multiway decomposed model achieves accuracy comparable to the\nfull model, while requiring only a small fraction of the memory and compute\ntime. The approach has implications for a majority of neuroimaging methods\nusing linear approximations to measured signals.\n